ramsi-k commited on
Commit
3d559dd
·
verified ·
1 Parent(s): 114cecc

Push agent to the Hub

Browse files
README.md CHANGED
@@ -17,7 +17,7 @@ model-index:
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
- value: -78.65 +/- 26.34
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -37,10 +37,10 @@ model-index:
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
- 'total_timesteps': 500000
41
  'learning_rate': 0.001
42
- 'num_envs': 16
43
- 'num_steps': 64
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.99
@@ -55,7 +55,7 @@ model-index:
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'ramsi-k/LunarLander-v2-fromscratch-tune'
58
- 'batch_size': 1024
59
- 'minibatch_size': 256}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -194.56 +/- 121.41
21
  name: mean_reward
22
  verified: false
23
  ---
 
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
+ 'total_timesteps': 50000
41
  'learning_rate': 0.001
42
+ 'num_envs': 64
43
+ 'num_steps': 32
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.99
 
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'ramsi-k/LunarLander-v2-fromscratch-tune'
58
+ 'batch_size': 2048
59
+ 'minibatch_size': 512}
60
  ```
61
 
logs/events.out.tfevents.1707299788.0afa5d2aa1c9.9401.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1af55fabfbdb6e8cd851f0c9b25930401834897ee2cf22e1521a21fe0b7476e
3
+ size 46963
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0f759c0c4aeb11bb0973490c5685b16a8dbed9550bbcb844b5b72bf3f05a3c5d
3
  size 42898
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3613c477808f9c136fa5bbb7b29a25e519dc5141e63cbe71e2bf23ce794d1cec
3
  size 42898
replay.mp4 CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
 
results.json CHANGED
@@ -1 +1 @@
1
- {"env_id": "LunarLander-v2", "mean_reward": -78.65222978619455, "std_reward": 26.33838393044832, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-07T09:51:49.750567"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -194.55892486331282, "std_reward": 121.41324374934395, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-07T09:56:48.349457"}